This is part 1 on Normalizing Flows.

**Introduction to Normalizing Flows**

- We consider the topic of modeling probability distributions given samples of that unknown distribution (generative modeling)
- Several methods in generative modeling exist. Popular, recent approaches are GANs and VAEs.
- Normalizing Flows are a new class of methods that transform a simple input distribution (e.g. Gaussian) into a complex distribution through a series of invertible mappings.
- Many types of such mappings have been proposed, e.g. linear, or 1x1 convolutions.
- Normalizing flows combine many advantageous features which a generative modeling technique should have: No restriction to a predetermined class of density functions, direct calculation of prob. densities in any point, trainable network parameters.

**Demo: Coupling Normalizing Flows in Python**